jambo6 / sepsis_competition_physionet_2019 Goto Github PK

I established the training dataset_A and dataset_B respectively by the code provided instead of using original dataset_AB. I evaluated the RNN example on dataset_A and dataset_B. I found that RNN learned nothing and predict all data as 0 on dataset B. I tried some positive weight on loss function but obtained unsatisfactory results. I wonder how to make it work.

I am interested in predicting/diagnosing Sepsis and came across your winning submission to the Physionet 2019 Challenge. Congrats!

I had a chance to go through results across Hospital A, B and C and observe that model is performing poorly on Hospital C [where no training data was provided]. Do you have any hypothesis on why that might be the case, and how the model could have generalized better?

Also if there was some training data available from Hospital C, do you think techniques like transfer learning could have been applied to generalize better?

Thanks for your input.
-Reddy